INDEX

Explanations

names after "of"

The neuron strongly activates on numeric tokens (numbers and measurements) in the text.

New Auto-Interp

Configuration

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

Negative Logits

</h4>

-1.80

-1.76

quilo

-1.70

 TAMBÉM

-1.69

ным

-1.67

这是一

-1.63

！”

-1.61

 Duft

-1.60

柺

-1.59

齜

-1.59

POSITIVE LOGITS

to

2.83

But

2.14

但

1.89

The

1.86

 They

1.75

 Then

1.70

的人物

1.69

 endgül

1.65

非常的

1.60

 soziale

1.55

Activations Density 0.020%